Empowerment of AI with Implantable Biosensors for The Pattern Recognition of Neurotransmitters
IBRAHIM MOUBARAK
PhD Student, Dept. of ECE
Clarkson University
Abstract: The real-time monitoring of neurochemicals like neurotransmitters (NTs) in the brain has become crucial for scientific research and medical applications over the past decade. To achieve this, biomedical informaticians are increasingly adopting data-driven approaches to estimate these neurochemicals in vivo. The primary objective of this research is to effectively utilize AI to improve the deconvolution of recorded interfering NT-signals from complex matrices, enabling the identification of the “true” signatures of specific NT-signaling. Cheminformatics, the application of AI in analytical chemistry, has been extensively employed to analyze data from biosensors integrated with traditional techniques such as chromatography, fluorometry, and spectroscopy. In contrast, electrochemical biosensors have emerged as promising tools for real-time, in situ applications due to their rapid responses, low cost, and ease of integration with portable devices. However, enhancing the sensitivity and selectivity of these electrochemical biosensors for in vivo applications, particularly in the brain, remains a challenge. Efforts to improve the selectivity and sensitivity of biosensors have involved modifying their functional surfaces using bioenzymes and nanoparticles, which are immobilized within a biocompatible matrix. This approach has shown promise for sensitive and selective detection of neurochemicals in complex in vivo environments. Nevertheless, challenges persist, as interferences arise between neurochemical species with similar molecular structures, sizes, and oxidation potentials, as well as from background noise. We propose the incorporation of machine learning and pattern recognition techniques to analyze data from implantable biosensors to 1) enhance their reliability in simultaneously monitoring neurotransmitter responses in complex matrices and 2) improve real-time, in situ discrimination of the “true” signatures of specific neurochemical signaling. Our focus is on differentiating dopamine from these complex matrices. Understanding the true in vivo response of dopamine has significant potential for future therapies, including closed-loop deep brain stimulation for managing neurological conditions such as Parkinson’s disease, depression, and Alzheimer’s
BIO: Ibrahim Moubarak is a PhD student and research assistant at the BIOSAL laboratory within the ECE department at Clarkson University. He also works as a teaching assistant in the mathematics department at the same institution. Before joining BIOSAL, he was a lecturer in the Electrical and Electronic Engineering department at the Islamic University of Technology in Bangladesh, where he earned both his BSc and MSc in electrical and electronic engineering. His research focuses on applying AI to analyze biological data for medical purposes. Currently, he is investigating the pattern recognition of neurotransmitters to enhance closed-loop deep brain stimulation for treating neurodegenerative diseases such as Parkinson’s, depression, and Alzheimer’s.
Tuesday, November 5, 2024, 12:15-1:15 pm, CAMP 194
Join Link: https://clarkson.zoom.us/j/97763004044?pwd=fReadMi2o7OYVOIOgYm5yAuGGnbmdy.1 Contact for queries: Prof Masudul Imtiaz, mimtiaz@clarkson.edu
*Co-Sponsored by IEEE student branch and HKN
________________________________________________________________
Electrical and Computer Engineering ● CLARKSON UNIVERSITY ● Potsdam, New York 13699-5720